news_checker.py

import os
from newsapi import NewsApiClient
from dotenv import load_dotenv
import pandas as pd
from datetime import datetime, timedelta

load_dotenv()

class NewsChecker:
    def __init__(self):
        self.api_key = os.getenv('NEWS_API_KEY')
        if not self.api_key:
            print("WARNING: NEWS_API_KEY not found in environment variables")
        else:
            print("NEWS_API_KEY found in environment variables")
            
        try:
            self.newsapi = NewsApiClient(api_key=self.api_key)
        except Exception as e:
            print(f"Error initializing NewsAPI client: {str(e)}")
        
    def get_recent_news(self):
        if not self.api_key:
            print("Cannot fetch news: No API key configured")
            return pd.DataFrame()
            
        try:
            # Get news from the last 7 days
            week_ago = (datetime.now() - timedelta(days=7)).strftime('%Y-%m-%d')
            response = self.newsapi.get_everything(
                q='',
                from_param=week_ago,
                language='en',
                sort_by='relevancy',
                page_size=100
            )
            
            if response['status'] == 'ok':
                articles = response['articles']
                # Extract titles and descriptions
                news_data = [
                    {
                        'title': article['title'],
                        'description': article['description']
                    }
                    for article in articles if article['description']
                ]
                print(f"Successfully fetched {len(news_data)} articles")
                return pd.DataFrame(news_data)
            else:
                print(f"NewsAPI response status was not 'ok': {response.get('status')}")
                return pd.DataFrame()
                
        except Exception as e:
            print(f"Error fetching news: {str(e)}")
            return pd.DataFrame()
    
    def check_content_against_news(self, marketing_text):
        news_df = self.get_recent_news()
        if news_df.empty:
            return {
                'status': 'warning',
                'message': 'Unable to check against current news context. Proceed with caution.'
            }
            
        # Simple keyword matching for demo purposes
        marketing_words = set(marketing_text.lower().split())
        potential_conflicts = []
        
        for _, row in news_df.iterrows():
            title_words = set(row['title'].lower().split())
            desc_words = set(str(row['description']).lower().split())
            
            # Check for significant word overlap
            if len(marketing_words.intersection(title_words)) >= 3:
                potential_conflicts.append(row['title'])
                
        if potential_conflicts:
            return {
                'status': 'warning',
                'message': 'Potential conflicts found with current news:\n- ' + '\n- '.join(potential_conflicts)
            }
            
        return {
            'status': 'pass',
            'message': 'No significant conflicts with current news found.'
        }